Patents by Inventor Krishna Pattipati
Krishna Pattipati has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20230106360Abstract: Systems and methods are disclosed for performing fault detection and prediction for power electronics and switching devices for power electronics, such as power inverters. Systems and methods disclosed herein can include determining, by a partial least squares model that evaluates values for one or more switching parameters for a switching device, the one or more switching parameters selected from a first set of switching parameters, a predicted value for the on-state current Ids of the switching device. The predicted value for the on-state current Ids can be based on the values of the one or more switching parameters for the switching device. Systems and methods disclosed herein can determine a residual comprising the difference between the predicted value for the another switching parameter of the switching device and an actual value of the predicted value for the another switching parameter, and generate a test statistic based on the residual.Type: ApplicationFiled: October 1, 2021Publication date: April 6, 2023Inventors: KRISHNA PATTIPATI, MUHAMED K. FAROOQ, QIAN YANG, ALI BAZZI, SHAILESH N. JOSHI, HIROSHI UKEGAWA
-
Publication number: 20230104896Abstract: Systems, methods, computer-readable media, techniques, and methodologies are disclosed for performing fault detection and prediction for power electronics and switching devices for power electronics. Systems and methods can determine, using a machine learning model, a prediction for a value of a first switching parameter of a switching device, the prediction based on the present value of a second switching parameter of a switching device and a prior value of the first switching parameter. Systems and methods disclosed herein can further determine a residual comprising the difference between the prediction and an actual value of the switching parameter, generate a test statistic based on the residual, and compare the test statistic to a first threshold value. Systems and methods disclosed herein can determine the presence of a fault in the switching device based on a comparison of the test statistic to a threshold value.Type: ApplicationFiled: October 1, 2021Publication date: April 6, 2023Inventors: KRISHNA PATTIPATI, MUHAMED K. FAROOQ, QIAN YANG, ALI BAZZI, SHAILESH N. JOSHI, HIROSHI UKEGAWA
-
Patent number: 11353861Abstract: A method, system, and non-transitory computer readable medium describing an autoencoder that creates a reduced feature space from healthy power electronics devices for training. Devices under test are then encoded and compared to the encoded features of the healthy devices to determine health of the other devices. Contextual information is used to build multiple models that compare power electronics devices from similarly operated vehicles with one another.Type: GrantFiled: May 4, 2020Date of Patent: June 7, 2022Assignees: TOYOTA MOTOR ENGINEERING & MANUFACTURING NORTH AMERICA, INC., UNIVERSITY OF CONNECTICUTInventors: Shailesh N. Joshi, Donald Mcmenemy, John Kaminski, Ravi Rajamani, Muhamed Farooq, Krishna Pattipati, Ali Bazzi
-
Patent number: 11340154Abstract: A system and method that determines whether a heat exchanger within a complex networked system is fouling is provided. The system and method includes training classifiers indicative of a plurality of fouling conditions associated with the heat exchanger and testing the classifiers with optimal sensor data from optimal sensors to determine whether the fouling is being experienced by the heat exchanger.Type: GrantFiled: September 16, 2020Date of Patent: May 24, 2022Assignee: THE UNIVERSITY OF CONNECTICUTInventors: Nayeff A. Najjar, Shalabh Gupta, James Z. Hare, Gregory R. Leaper, Paul M. D'Orlando, Rhonda Walthall, Krishna Pattipati
-
Patent number: 11293981Abstract: Systems and methods of testing the health of vehicular power devices are disclosed herein. A method may include producing operating points as a function of cycling current (Ids) and voltage drain to source (Vds) when a subject device is conducting current. The method may further include determining a mean of moving distribution to adapt a center of the moving distribution contrasted with a plurality of known healthy devices. The method may also include indicating an imminent fault in the subject device based upon a discontinuity among operating points above a threshold.Type: GrantFiled: January 15, 2020Date of Patent: April 5, 2022Assignees: Toyota Motor Engineering & Manufacturing North America, Inc., University of ConnecticutInventors: Donald McMenemy, John Kaminski, Shailesh N. Joshi, Ali M. Bazzi, Krishna Pattipati
-
Patent number: 11169899Abstract: To predict a failure condition in a power module of a vehicle, it is determined whether a discontinuity in statistical data characterizing physical measurements of the power module meets a threshold criterion. Responsive to the discontinuity meeting the threshold criterion, a data offset in the physical measurements is computed at the discontinuity. A shift correction is applied to the physical measurements in accordance with the computed data offset responsive to a determination that the discontinuity is attributable to a restart of the power module. Other statistical data characterizing the shift-corrected physical measurements are computed and the statistical data and the other statistical data are provided to a machine learning processor that predicts the failure condition in the power module.Type: GrantFiled: April 15, 2019Date of Patent: November 9, 2021Assignees: Toyota Motor Engineering & Manufacturing North America, Inc., University of ConnecticutInventors: Ali M. Bazzi, Lingyi Zhang, Weiqiang Chen, Krishna Pattipati, Donald McMenemy, Shailesh Joshi
-
Publication number: 20210341911Abstract: A method, system, and non-transitory computer readable medium describing an autoencoder that creates a reduced feature space from healthy power electronics devices for training. Devices under test are then encoded and compared to the encoded features of the healthy devices to determine health of the other devices. Contextual information is used to build multiple models that compare power electronics devices from similarly operated vehicles with one another.Type: ApplicationFiled: May 4, 2020Publication date: November 4, 2021Applicants: TOYOTA MOTOR ENGINEERING & MANUFACTURING NORTH AMERICA, INC., UNIVERSITY OF CONNECTICUTInventors: Shailesh N. JOSHI, Donald MCMENEMY, John KAMINSKI, Ravi RAJAMANI, Muhamed FAROOQ, Krishna PATTIPATI, Ali BAZZI
-
Publication number: 20210216876Abstract: Systems and methods of auto-encoder behavior modelling of vehicle components are described herein. A method for electronic device health prediction may include encoding input data into a reduced feature set via an auto-encoder as part of an artificial neural network. The method may further include decoding the reduced feature set. The method may also include reading the reduced feature set as output. The method may still further include encoding features of a subject device and other devices, wherein at least one of the other devices is designated as a healthy device. The method may additionally include associating the features of the other devices with a healthy device cluster based on a threshold distance. The method may also additionally include associating the features of the subject device with the healthy device cluster, wherein the subject device is flagged as faulty based upon exceeding the threshold distance from the healthy device cluster.Type: ApplicationFiled: January 15, 2020Publication date: July 15, 2021Applicants: TOYOTA MOTOR ENGINEERING & MANUFACTURING NORTH AMERICA, INC., UNIVERSITY OF CONNECTICUTInventors: Donald McMenemy, John Kaminski, Shailesh N. Joshi, Ali M. Bazzi, Krishna Pattipati
-
Publication number: 20210215760Abstract: Systems and methods of testing the health of vehicular power devices are disclosed herein. A method may include producing operating points as a function of cycling current (Ids) and voltage drain to source (Vds) when a subject device is conducting current. The method may further include determining a mean of moving distribution to adapt a center of the moving distribution contrasted with a plurality of known healthy devices. The method may also include indicating an imminent fault in the subject device based upon a discontinuity among operating points above a threshold.Type: ApplicationFiled: January 15, 2020Publication date: July 15, 2021Applicants: TOYOTA MOTOR ENGINEERING & MANUFACTURING NORTH AMERICA, INC., UNIVERSITY OF CONNECTICUTInventors: Donald McMenemy, John Kaminski, Shailesh N. Joshi, Ali M. Bazzi, Krishna Pattipati
-
Patent number: 10895523Abstract: A system and method that determines whether a heat exchanger within a complex networked system is fouling is provided. The system and method includes training classifiers indicative of a plurality of fouling conditions associated with the heat exchanger and testing the classifiers with optimal sensor data from optimal sensors to determine whether the fouling is being experienced by the heat exchanger.Type: GrantFiled: April 30, 2015Date of Patent: January 19, 2021Assignee: THE UNIVERSITY OF CONNECTICUTInventors: Nayeff A. Najjar, Shalabh Gupta, James Z. Hare, Gregory R. Leaper, Paul M. D'Orlando, Rhonda Walthall, Krishna Pattipati
-
Publication number: 20200408669Abstract: A system and method that determines whether a heat exchanger within a complex networked system is fouling is provided. The system and method includes training classifiers indicative of a plurality of fouling conditions associated with the heat exchanger and testing the classifiers with optimal sensor data from optimal sensors to determine whether the fouling is being experienced by the heat exchanger.Type: ApplicationFiled: September 16, 2020Publication date: December 31, 2020Inventors: Nayeff A. Najjar, Shalabh Gupta, James Z. Hare, Gregory R. Leaper, Paul M. D'Orlando, Rhonda Walthall, Krishna Pattipati
-
Publication number: 20200351504Abstract: Devices, computer-readable media, and methods for differential adaptive bitrate streaming based on scene complexity are disclosed. In one example, a method includes inferring, by a processor, a complexity of a scene contained in a first chunk of an adaptive bitrate streaming video, wherein the first chunk is a next chunk of the adaptive bitrate streaming video to be downloaded to an adaptive bitrate streaming video player, and wherein the complexity indicates a relative amount of spatial and temporal information contained in the scene, and selecting, by the processor, a first track from which to download the first chunk, wherein the first track is one of a plurality of tracks containing the first chunk, and wherein each track of the plurality of tracks encoded the first chunk at a different bitrate, and wherein a bitrate of the first track is proportional to the complexity of the scene as inferred.Type: ApplicationFiled: May 3, 2019Publication date: November 5, 2020Inventors: Subhabrata Sen, Shuai Hao, Krishna Pattipati, Yanyuan Qin, Bing Wang
-
Patent number: 10827181Abstract: Devices, computer-readable media, and methods for differential adaptive bitrate streaming based on scene complexity are disclosed. In one example, a method includes inferring, by a processor, a complexity of a scene contained in a first chunk of an adaptive bitrate streaming video, wherein the first chunk is a next chunk of the adaptive bitrate streaming video to be downloaded to an adaptive bitrate streaming video player, and wherein the complexity indicates a relative amount of spatial and temporal information contained in the scene, and selecting, by the processor, a first track from which to download the first chunk, wherein the first track is one of a plurality of tracks containing the first chunk, and wherein each track of the plurality of tracks encoded the first chunk at a different bitrate, and wherein a bitrate of the first track is proportional to the complexity of the scene as inferred.Type: GrantFiled: May 3, 2019Date of Patent: November 3, 2020Assignees: AT&T INTELLECTUAL PROPERTY I, L.P., THE UNIVERSITY OF CONNECTICUTInventors: Subhabrata Sen, Shuai Hao, Krishna Pattipati, Yanyuan Qin, Bing Wang
-
Publication number: 20200327033Abstract: To predict a failure condition in a power module of a vehicle, it is determined whether a discontinuity in statistical data characterizing physical measurements of the power module meets a threshold criterion. Responsive to the discontinuity meeting the threshold criterion, a data offset in the physical measurements is computed at the discontinuity. A shift correction is applied to the physical measurements in accordance with the computed data offset responsive to a determination that the discontinuity is attributable to a restart of the power module. Other statistical data characterizing the shift-corrected physical measurements are computed and the statistical data and the other statistical data are provided to a machine learning processor that predicts the failure condition in the power module.Type: ApplicationFiled: April 15, 2019Publication date: October 15, 2020Applicants: Toyota Motor Engineering & Manufacturing North America, Inc., University of ConnecticutInventors: Ali M. BAZZI, Lingyi Zhang, Weiqiang Chen, Krishna Pattipati, Donald McMenemy, Shailesh Joshi
-
Patent number: 10664562Abstract: A method includes calculating a first estimated state of charge (SOC) of a battery at a first time, receiving a voltage value representing a measured voltage across the battery at a second time, calculating a filter gain at the second time, and calculating a second estimated SOC of the battery at the second time based on the first estimated SOC, the voltage value, and the filter gain. Another method includes storing, in a memory, a library of equivalent circuit models representing a battery, determining an operational mode of a battery based on a load associated with the battery, selecting one of the equivalent circuit models based on the determined operational mode, and calculating a state of charge of charge (SOC) of the battery using the selected equivalent circuit model.Type: GrantFiled: February 20, 2014Date of Patent: May 26, 2020Assignee: Fairchild Semiconductor Corporation and University of ConnecticutInventors: Balakumar Balasingam, Brian French, Yaakov Bar-Shalom, Bharath Pattipati, Krishna Pattipati, James Meacham, Travis Williams, Gopi Vinod Avvari, Tai-Sik Hwang
-
Publication number: 20140244193Abstract: A method includes calculating a first estimated state of charge (SOC) of a battery at a first time, receiving a voltage value representing a measured voltage across the battery at a second time, calculating a filter gain at the second time, and calculating a second estimated SOC of the battery at the second time based on the first estimated SOC, the voltage value, and the filter gain. Another method includes storing, in a memory, a library of equivalent circuit models representing a battery, determining an operational mode of a battery based on a load associated with the battery, selecting one of the equivalent circuit models based on the determined operational mode, and calculating a state of charge of charge (SOC) of the battery using the selected equivalent circuit model.Type: ApplicationFiled: February 20, 2014Publication date: August 28, 2014Applicants: Fairchild Semiconductor Corporation, The University of ConnecticutInventors: Balakumar BALASINGAM, Brian FRENCH, Yaakov BAR-SHALOM, Bharath PATTIPATI, Krishna PATTIPATI, James MEACHAM, Travis WILLIAMS, Gopi Vinod AVVARI, Tai-Sik HWANG
-
Publication number: 20140244225Abstract: A method includes calculating a first estimated state of charge (SOC) of a battery at a first time, receiving a voltage value representing a measured voltage across the battery at a second time, calculating a filter gain at the second time, and calculating a second estimated SOC of the battery at the second time based on the first estimated SOC, the voltage value, and the filter gain. Another method includes storing, in a memory, a library of equivalent circuit models representing a battery, determining an operational mode of a battery based on a load associated with the battery, selecting one of the equivalent circuit models based on the determined operational mode, and calculating a state of charge of charge (SOC) of the battery using the selected equivalent circuit model.Type: ApplicationFiled: February 20, 2014Publication date: August 28, 2014Applicants: The University of Connecticut, Fairchild Semiconductor CorporationInventors: Balakumar BALASINGAM, Brian FRENCH, Yaakov BAR-SHALOM, Bharath PATTIPATI, Krishna PATTIPATI, James MEACHAM, Travis WILLIAMS, Gopi Vinod AVVARI, Tai-Sik HWANG
-
Publication number: 20100222897Abstract: A distributed diagnosis algorithm based on a multi-signal digraph model of an overall system is provided. In addition, a model enables the generation of a fault-test dependency matrix (D-matrix), which summarizes the detection capabilities of tests designed for faults associated with each node. Each row represents a fault state and each column represents a test.Type: ApplicationFiled: March 2, 2009Publication date: September 2, 2010Applicants: Toyota Motor Engineering & Manufacturing North America, Inc., The University of ConnecticutInventors: Liu Qiao, Krishna Pattipati, Setu Madhavi Namburu, Danil V. Prokhorov